AI Safety Engineer: Guardrails, Alignment & Testing
Hyphen Connect
Hyphen Connect is seeking an AI Safety Specialist in San Francisco, California, to enhance the security of language models. The successful candidate will conduct adversarial testing, implement protective measures, and develop constitutional AI principles to align AI behavior with ethical standards. Candidates should have a background in cybersecurity or adversarial machine learning, along with an analytical mindset for identifying edge cases. This role focuses on ensuring the safe deployment of AI systems. #J-18808-Ljbffr Hyphen Connect
Vacancy posted 4 days ago
Similar jobs that could be interesting for youBased on the AI Safety Engineer: Guardrails, Alignment & Testing in San Francisco, CA vacancy
- ...are searching for an AI Safety Specialist who will play... ...adversarial testing, implementing protective measures, and aligning AI behavior with ethical... ...multimodal agents. Implement guardrails and real-time filtering... ...cybersecurity, prompt engineering, or adversarial ML....Suggested
Hyphen Connect Limited
San Francisco, CA3 days ago - Reflection is seeking a highly skilled safety researcher to own red-teaming and... ...failure modes across security, misuse, and alignment, shaping guardrails with the Alignment team. You will... ...releases, balancing risk with ambitious AI capabilities. #J-18808-Ljbffr Visa HuntSuggested
- ...Capital in San Francisco is looking for individuals passionate about AI safety to own the red-teaming and adversarial evaluation pipeline for their models. The role involves collaborating with the Alignment team and ensuring all releases meet safety thresholds. Candidates...Suggested
$160k - $207k
...s written and provides guardrails that pave the road for... ...smarter as you build, with AI that learns your... ...in Application Security Testing and is trusted by leading... ...About the role As an AI engineer, you’ll apply LLM... ...a competitive, market-aligned benefits program that meets...SuggestedFull timeCurrently hiringLocal areaRemote workWeekend work3 days per weekSemgrep
San Francisco, CA1 day ago$203.5k
...Job Title Lead, AI Engineering Job ID 102641... ...processes for automated testing, regression evaluation... ...improvementBalance performance, safety, responsible AI... ...design:Implement guardrails, fallbacks, red-... ...ethics teams to ensure alignment with Bain’s Responsible...SuggestedPermanent employmentFull timeApprenticeshipWork at officeLocal areaWork from homeHome office3 days per week- Hyphen Connect Limited is seeking an AI Safety Specialist in San Francisco, California, to enhance the... ...models. This role involves conducting adversarial testing, implementing protective measures, and ensuring AI behavior aligns with ethical principles. The ideal candidate...
- ...solutions while advancing AI-empowered software... ..., comprised of engineers, product leaders,... ...on code, pressure-testing ideas with real... ..., patterns, and guardrails that integrate generative... ....* Manage GenAI-aligned teams: Orchestrate... ...AI governance, or safety practices.*...Temporary workLocal area
$293.5k
...Expert Senior Manager, AI Engineering Job ID 104335... ...processes for automated testing, regression... ...improvementBalance performance, safety, responsible AI... ...system design:Implement guardrails, fallbacks, red-... ...ethics teams to ensure alignment with Bain’s Responsible...Permanent employmentFull timeApprenticeshipWork at officeLocal areaWork from homeHome office3 days per week$221k - $247k
...ourTotal Rewards philosophy.AI is a fundamental part... ...and risk outcomes.Align roadmap priorities with... ...accuracy and hallucination testing, human-in-the-loop... ...EnablementPartner with EAIT engineers, administrators, AI... ...responsible-AI practices: guardrails, privilege protection,...Full timeContract workWork at officeLocal areaShift work2 days per week3 days per week$190.2k - $360.5k
...looking for a Principal AI Systems Engineer with deep C++... ...and cross-functional alignment. C++ Platform and Integration... ...refactoring, better testing, and stronger... ...performance, memory safety, reliability, backward... ...review loops. Define guardrails for AI-driven actions...Full timeTemporary workLocal areaRemote workWorldwide$124k - $171k
...next.Job Title:Senior AI Automation EngineerCompany... ...Senior AI Automation Engineer accelerates the... ...workflows, evaluation, guardrails, human review, and workflow... ...implementing testing, evaluation, monitoring... ...as internal equity and alignment with market data.#LI-TA...Full timeContract workFor contractors- ...Everyone's building AI agents, but almost nobody gets them to... ...governance, and trust become the real engineering challenge. Arcade is the... ..., write the integration code, test it against real API behavior,... ...and benefits. Compensation is aligned with the range below and...Full timeShift work
Arcade
San Francisco, CA1 day ago $150k - $250k
...About Distyl AI Distyl is an applied AI technology company partnering... ...What We Are Looking For AI Engineers build and operate production... ...coherent production systems aligned with user and SME needs... ...Build evaluation frameworks, test cases, feedback mechanisms, and...Full timeWork at officeFlexible hours3 days per weekDistyl Ai
San Francisco, CA1 day ago$148k - $185k
...the TeamThe Risk Tech engineering organization is committed... ...costs to enhance the safety and affordability of rides... ...management systems, aligning priorities with Product... ...resolving pain points with AI automation... ...high quality and well-tested solutions and code.Collaborate...Hourly payWork experience placementWork at officeLocal area3 days per week- ...product management, design, and engineering together with the autonomy to... ...Are You are an exceptional AI-native software engineer who... ...context and constraints, establish tests and evaluations, and review... ..., observability, and guardrails. Build products that perform...Permanent employmentFull timeWork experience placementLive inWork at officeLocal area
- ...AI at Zapier At Zapier , we build and use automation... ...as a Sr. Applied AI Engineer ! As a key member of... ...lifecycle of building, testing, deploying, and scaling... ..., and operational guardrails. Design and implement... ...performance, reliability, safety, and cost efficiency of...Remote jobFull time
Zapier
San Francisco, CA1 day ago $110.7k - $372.9k
...need. Deloitte has a new AI-first effort, backed by... ...lab. As an Agentic AI Engineer, you will design, build... ..., evaluation & safety • Implement observability... ...production behavior. • Apply guardrails, safety controls, and... ...analysis, and sandboxed test environments — alongside...Local areaVisa sponsorship- ...About the Team GTM Growth Engineering builds AI-native products that help OpenAI... ..., tools, routing, guardrails, or workflow design. Design... ...evaluation design, regression testing, human or model grading,... ...that must be created with safety and human needs at its core...Full time
OpenAI
San Francisco, CA1 day ago $180k - $215k
...technology. The flagship product—an AI-driven, non-invasive cardiac test supported by the ACC/AHA Chest Pain... ...and greenfield product engineering. You won't just be consuming AI models... ...cleared software.Implement advanced guardrails, evaluation frameworks, and reasoning...Local areaWorldwideRelocation$239.2k - $270k
...everywhere. We are actively seeking a Staff AI Security Engineer to join our team. Reporting to the... ...Build scalable AI security guardrails and tooling that enable safe experimentation... ...prior to GA ~80% of AI features are tested by the AI Red Team or equivalent adversarial...Full timeWork at officeSleeping nights2 days per week3 days per weekSpring Health
San Francisco, CA1 day ago$102k - $125k
...By blending design, product engineering, analytics, and automation,... ...design and deliver innovative AI/ML and agentic AI solutions... ...and agent pipelines, CI/CD, testing, deployment, observability,... ...integrity for GenAI systems* Build guardrails for safety, compliance, and performance...Temporary workWork at officeLocal areaFlexible hours$154.39k - $247.02k
...pursuing society’s most critical safety and justice issues with our... ...a company where you matter.AI Infrastructure Engineer, Corporate AI TeamTeam &... ...processes.Partner through testing, rollout, UAT, and long-... ...Data, and Corporate AI to align infrastructure patterns with...Work experience placement$73.5k - $212.28k
...people in data and analytics engineering focus on leveraging advanced... ...OpportunityAs part of the People Tech & AI team you will lead the design... ...and enforcing automated testing strategies- Architecting,... ...and AI-enabled platforms aligned to PwC People Tech & AI strategyTravel...Full timeWork experience placementH1bRemote work$200k - $250k
About Distyl AI Distyl is an applied AI technology company partnering... ...0s. What We Are Looking ForAI Engineers, Enterprise Lead are senior... ...leaders, and keep teams aligned without becoming a bottleneckTalent... ...architecture, debugging, testing, observability, performance, maintainability...Work at office3 days per week- ...a Staff Machine Learning Engineer with deep expertise in agentic AI — and a true passion for... ...creation — to design, build, test, evaluate, and... ...rigorous evaluation and safety frameworks — automated testing... ...adversarial testing, safety guardrails, observability (tracing,...Full time
Medeloop
San Francisco, CA1 day ago $192k - $259.8k
...collaboration days where teams align, strategize, and innovate.... ...news. Job Summary: Drata's AI Platform team builds the production... ...our agent developers, product engineers, and an embedded SRE partner,... ...), prompt versioning and A/B testing, AI workflow deployment with...Full timeWork at officeImmediate startWorldwideMonday to FridayFlexible hoursDrata
San Francisco, CA1 day ago- ...We prioritize candidate safety. Please be aware that... ...About the roleThe Growth Engineering team builds world-class... ...infrastructure, and AI systems powering Rippling... ...evaluation datasets, regression tests, and quality metrics so... ...employees will be aligned with one of the ranges...Work at office3 days per week
$145.5k - $249.5k
...connected system. We remove friction and drive alignment between care providers and payers, and... .... Growing together. As a Lead AI/ML Engineer on the AI Platform Team within Optum AI... ...routine tasks, conduct code reviews, perform testing, and drive continuous improvementEnsure...Minimum wageFull timeWork experience placementWork at officeLocal areaRemote work$174k - $253k
...Computer Science, a related Software Engineering field, or equivalent practical... ...to applied research to improve the safety and alignment of frontier AI systems. Experience with training... ...allowing them to setup large-scale tests and deploy promising ideas quickly and...Full timeDeepMind
San Francisco, CA17 days ago$91.1k - $179.5k
...our clients’ success. We are hiring an AI Engineer to build and operate the data, features,... ...future of Human Capital by building market-aligned products, platforms, and services that... ...security.2+ years of experience with treat testing, monitoring, and operational readiness...Local area
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to AI Safety Engineer: Guardrails, Alignment & Testing. Be the first to apply!
Related searches
- ai ml engineer San Francisco, CA
- machine learning ai engineer San Francisco, CA
- ai developer San Francisco, CA
- ai engineer San Francisco, CA
- ai research engineer San Francisco, CA
- ai prompt engineer San Francisco, CA
- senior ai engineer San Francisco, CA
- ai engineer remote San Francisco, CA
- safety engineer San Francisco, CA
- public health engineer San Francisco, CA